PInVerify: An Offline Embodied Benchmark for Active Instance Verification

• URL: http://arxiv.org/abs/2605.30639v1
• Date: Thu, 28 May 2026 22:42:38 GMT
• Title: PInVerify: An Offline Embodied Benchmark for Active Instance Verification
• Abstract summary: Embodied agents have made strong progress in navigating to target objects, but reaching the goal vicinity does not guarantee that the agent has found the correct instance.<n>We address this gap with Active Instance Verification (AIV), a task in which an agent actively selects viewpoints around a candidate object to decide whether it matches a fine-grained natural-language description.<n>We introduce PInVerify, an offline embodied benchmark for AIV: 3,000 evaluation episodes across 18 object categories, delivered as multi-view captures.
• Score: 8.403971471573607
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Embodied agents have made strong progress in navigating to target objects, but reaching the goal vicinity does not guarantee that the agent has found the correct instance: subtle attribute differences (e.g., "white floral" vs. "white striped") often require close-range, multi-view inspection. We address this gap with Active Instance Verification (AIV), a task in which an agent actively selects viewpoints around a candidate object to decide whether it matches a fine-grained natural-language description. We formalize AIV as a finite-horizon decision process and introduce PInVerify, an offline embodied benchmark for AIV: 3,000 evaluation episodes across 18 object categories, delivered as multi-view captures with a 6-sector navigation topology that exposes trap views (navigable but uninformative) and unreachable sectors. As reference baselines we build a training-free pipeline and a LoRA-fine-tuned end-to-end agent around open-source multimodal large language models (MLLMs) at on-device scale ($\leq$8B parameters), with attribute decomposition, a visibility-weighted multi-view tracker, and three next-best-view (NBV) strategies. In our evaluation across Qwen3-VL (4B/8B), SenseNova-SI-1.2-InternVL3-8B, CLIP, and SigLIP2, the best MLLM-based baseline exceeds the best embedding baseline by 4.9 pp; GT-box ablations show a +3.1 pp detection gap; and we do not observe reliable gains from active viewpoint selection within the tested NBV strategies. A LoRA-fine-tuned agent (SFT+GSPO) reaches 85.6%. PInVerify aims to support further work on active, fine-grained semantic verification in embodied AI. Code: https://github.com/Avalon-S/PInVerify.

Related papers

• Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit [8.665845754660458]
  AI-generated video detection GenVidBench and AIGVDBench are the de facto leaderboards.<n>Most evaluation protocols leave uncontrolled confounds that can inflate reported generalizations.<n>A 20-paper survey finds none applying all six standard controls that would catch this.<n>We combine them into an audited protocol and apply it to six representative feature sources.
  arXiv  Detail & Related papers  (2026-06-30T00:29:53Z)
• AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation [40.254835073578484]
  AnomalyClaw is a training-free visual anomaly detection agent.<n>It turns anomaly judgment into a multi-round refutation process.<n>It achieves consistent macro-AUROC improvements over single-step direct inference.
  arXiv  Detail & Related papers  (2026-05-11T11:40:07Z)
• COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm [59.26203051651017]
  C-TAO is the first continuously annotated training set for Open-Vocabulary Multi-Object Tracking (OVMOT)<n>For the framework bottleneck, we propose COVTrack++, a synergistic framework that achieves a bidirectional reciprocal mechanism between detection and association through three modules.<n>Experiments on TAO demonstrate state-of-the-art performance, with novel TETA reaching 35.4% and 30.5% on validation and test sets, improving novel AssocA by 4.8% and novel LocA by 5.8% over previous methods.
  arXiv  Detail & Related papers  (2026-03-25T07:20:27Z)
• Synthesizing the Kill Chain: A Zero-Shot Framework for Target Verification and Tactical Reasoning on the Edge [12.201060368447251]
  This paper introduces a hierarchical, zero-shot framework that cascades lightweight object detection with compact Vision-Language Models (VLMs)<n>We evaluate this pipeline on 55 high-fidelity synthetic videos from Battlefield 6 across three tasks: false-positive filtering (up to 100% accuracy), damage assessment (up to 97.5%), and fine-grained vehicle classification (55-90%)
  arXiv  Detail & Related papers  (2026-02-10T23:00:19Z)
• Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning [57.082554323521464]
  We propose a Sensitivity-aware Task Vector insertion framework (STV) to figure out where and what to insert.<n>Our key insight is that activation deltas across query-context pairs exhibit consistent structural patterns, providing a reliable cue for insertion.<n>Based on the identified sensitive-aware locations, we construct a pre-clustered activation bank for each location by clustering the activation values, and then apply reinforcement learning to choose the most suitable one to insert.
  arXiv  Detail & Related papers  (2025-11-11T13:42:13Z)
• Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels [40.571133087275406]
  Multi-agent collaborative dataset, which involves the sharing of complementary observations among agents, holds the potential to break through this bottleneck.<n>We introduce a novel unsupervised method that learns to Detect Objects from Multi-Agent LiDAR scans, termed DOtA, without using labels from external.<n>DOtA uses the complementary observations between agents to perform multi-scale encoding on preliminary labels, then decodes high-quality and low-quality labels.
  arXiv  Detail & Related papers  (2025-03-11T13:34:35Z)
• PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection [65.84604846389624]
  We propose PointOBB-v3, a stronger single point-supervised OOD framework.<n>It generates pseudo rotated boxes without additional priors and incorporates support for the end-to-end paradigm.<n>Our method achieves an average improvement in accuracy of 3.56% in comparison to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-23T18:18:15Z)
• Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation [40.803251337200656]
  Annotator is a general and efficient active learning baseline. voxel-centric online selection strategy is tailored to efficiently probe and annotate the salient and exemplar voxel girds within each LiDAR scan. Annotator excels in diverse settings, with a particular focus on active learning (AL), active source-free domain adaptation (ASFDA), and active domain adaptation (ADA)
  arXiv  Detail & Related papers  (2023-10-31T09:04:39Z)
• Exploring Active 3D Object Detection from a Generalization Perspective [58.597942380989245]
  Uncertainty-based active learning policies fail to balance the trade-off between point cloud informativeness and box-level annotation costs. We propose textscCrb, which hierarchically filters out the point clouds of redundant 3D bounding box labels. Experiments show that the proposed approach outperforms existing active learning strategies.
  arXiv  Detail & Related papers  (2023-01-23T02:43:03Z)
• VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention [32.44687996180621]
  We propose to adaptively fuse multi-view features in a global spatial context via Dual Cross-VIew SpaTial Attention (VISTA) The proposed VISTA is a novel plug-and-play fusion module, wherein the multi-layer perceptron widely adopted in standard attention modules is replaced with a convolutional one. At the time of submission, our method achieves 63.0% in overall mAP and 69.8% in NDS on the nuScenes benchmark, outperforming all published methods by up to 24% in safety-crucial categories such as cyclist.
  arXiv  Detail & Related papers  (2022-03-18T02:34:59Z)
• Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning [126.57680291438128]
  We study whether scalability can be achieved via a disentangled representation. We evaluate semantic tracklets' on the visual multi-agent particle environment (VMPE) and on the challenging visual multi-agent GFootball environment. Notably, this method is the first to successfully learn a strategy for five players in the GFootball environment using only visual data.
  arXiv  Detail & Related papers  (2021-08-06T22:19:09Z)
• Segment as Points for Efficient Online Multi-Object Tracking and Segmentation [66.03023110058464]
  We propose a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation. Our method generates a new tracking-by-points paradigm where discriminative instance embeddings are learned from randomly selected points rather than images. The resulting online MOTS framework, named PointTrack, surpasses all the state-of-the-art methods by large margins.
  arXiv  Detail & Related papers  (2020-07-03T08:29:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.